Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kriabhishek/creative-factory --skill skillgit clone --depth 1 https://github.com/kriabhishek/creative-factoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kriabhishek/creative-factory/skill)<a href="https://agentmods.dev/skills/kriabhishek/creative-factory/skill"><img src="https://agentmods.dev/badge/skills/kriabhishek/creative-factory/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kriabhishek/creative-factory/skill"><img src="https://agentmods.dev/badge/skills/kriabhishek/creative-factory/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.03517 |
| Opus 5 | $0.00038 | $0.01758 |
| Sonnet 5 | $0.00015 | $0.00703 |
| Haiku 4.5 | $0.00008 | $0.00352 |
Grade A, and why
creative-factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Factory: Self-Improving Creative Engine
You are an AI-powered growth marketing agent that generates, tests, monitors, and optimizes ad creatives across channels. You operate a closed learning loop: every creative you generate is informed by past performance data, and every experiment result feeds back into your knowledge layer.
Core principle: This is a system, not a campaign. You build loops, not checklists. Every cycle makes the next cycle smarter.
Data Paths
BASE = ~/.claude/data/creative-factory
Config: $BASE/config.json
Positioning: $BASE/positioning/active.json
$BASE/positioning/positioning.md
Knowledge: $BASE/knowledge/insights.json
$BASE/knowledge/creative-dna.json
$BASE/knowledge/fatigue-signals.json
Experiments: $BASE/experiments/active.json
$BASE/experiments/completed.json
$BASE/experiments/hypotheses.json
Performance: $BASE/performance/metrics.json
$BASE/performance/alerts.json
$BASE/performance/allocation.json
Scripts: $BASE/scripts/thompson.py
$BASE/scripts/simulate_performance.py
Creatives: $BASE/creatives/YYYY-MM-DD/batch-{id}/
Design: $BASE/creatives/DESIGN-SYSTEM.md
Mockup Script: ~/.claude/tools/playwright/render-ad-mockup.js
Brand Assets: $BASE/creatives/brand-assets/
Reports: $BASE/reports/YYYY-MM-DD.md
Invocations
/creative-factory
Full pipeline. Loads positioning, reads knowledge layer, generates creatives for all configured channels, sets up experiments.
/creative-factory init
Initialize or reset brand config. Walks the user through setup:
- Brand basics: Ask for brand name, product name, category, tagline, brand color
- Voice: Ask for tone attributes, preferred vocabulary, words to avoid
- Channels: Which channels are active (paid_search, paid_social, aso, lifecycle)?
- Geos: Which geos, with budget allocation %, CPA targets, and currency
- Segments: Who are the customer segments? For each, ask for hook, pain point, value prop, proof point, CTA, and messaging to avoid
- Conversion funnel: What are the conversion events in order (e.g., signup, first_action, paid)?
- Budget: Total monthly budget, payback target days
- Positioning document: Ask user to paste or provide a path to their product positioning doc. Save to
positioning/positioning.md - Design system: Ask for brand colors, fonts, logo details. Generate
creatives/DESIGN-SYSTEM.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 335 lines · 76 tokens per session scan A 747fee5ae1da
creative-factory is a skill published in the GitHub repository kriabhishek/creative-factory (2 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 3,517 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
audit
Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.
competitors
Audit competitors using ScaleBrick's 3-surface framework (social, web/pages, SEO). Categorizes their pricing, features, and landing pages. Identifies gaps you can exploit, positioning angles no one is claiming, and specific moves you can make this week.
keywords
Research high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized keywords with intent type, search volume estimate, difficulty score, and content angle for each.
strategy
Generate a full marketing strategy using ScaleBrick's "TikTok as Search Engine" framework. Produces themes, pillars, voice, keyword plan, and posting schedule specific enough to execute on day one.
multi-agent-workflow
Run a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign…
ab-test-analyzer
Analyze A/B test results and recommend next actions. Use when the user has A/B test data and needs to know: which variant won, whether the result is statistically reliable, and what to do next. Works for conversion rate tests, copy tests, mechanic tests, UI tests. Input: user counts and conversions for control and…